Peter B.<p>For my <a href="https://mastodon.social/tags/FIAF" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FIAF</span></a> presentation & workshop in Bologna end of the week, I've put together a clean "<a href="https://mastodon.social/tags/PlugAndPlayAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PlugAndPlayAI</span></a>" setup:</p><p><a href="https://mastodon.social/tags/USB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>USB</span></a> <a href="https://mastodon.social/tags/LiveDistro" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LiveDistro</span></a>: <a href="https://mastodon.social/tags/MXLinux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MXLinux</span></a> <a href="https://mastodon.social/tags/GNU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GNU</span></a> <a href="https://mastodon.social/tags/Debian" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Debian</span></a> with <a href="https://mastodon.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a>, <a href="https://mastodon.social/tags/LLava" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLava</span></a> and <a href="https://mastodon.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> in <a href="https://mastodon.social/tags/Docker" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Docker</span></a> and <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> files on another USB3 <a href="https://mastodon.social/tags/nvme" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nvme</span></a> </p><p>Fast like a local install. Given enough RAM and CPU/GPU.</p><p>Scary how easy it is to do that.</p><p>Bonus: Creates self-replicating <a href="https://mastodon.social/tags/ISO" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ISO</span></a> boot images of itself (in current configuration) in less than 5 minutes. 🤯 😎 .</p><p>Wow.</p>
Recent searches
No recent searches
Search options
Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.
Administered by:
Server stats:
227active users
eupolicy.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.3.8
#openwebui
0 posts · 0 participants · 0 posts today
Stéphane Klein<p>Je commence un nouveau petit side project « Setup une instance personnelle d'Open WebUI connectée à OpenRouter »</p><p><a href="https://notes.sklein.xyz/Projet%2030/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">notes.sklein.xyz/Projet%2030/</span><span class="invisible"></span></a></p><p><a href="https://social.coop/tags/SideProject" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SideProject</span></a> <a href="https://social.coop/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> <a href="https://social.coop/tags/OpenRouterAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenRouterAI</span></a> <a href="https://social.coop/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://social.coop/tags/generativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>generativeAI</span></a></p>
Netzpalaver<p>Cyberkriminelle nutzen falsch konfiguriertes KI-Tool, um KI-generierte Payloads auszuführen</p><p><a href="https://social.tchncs.de/tags/Bedrohungserkennung" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Bedrohungserkennung</span></a> <a href="https://social.tchncs.de/tags/Cryptominer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cryptominer</span></a> <a href="https://social.tchncs.de/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cybersecurity</span></a> <a href="https://social.tchncs.de/tags/Fehlkonfiguration" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Fehlkonfiguration</span></a>#LLM <a href="https://social.tchncs.de/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> <a href="https://social.tchncs.de/tags/Schwachstelle" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Schwachstelle</span></a> @Sysdig <a href="https://social.tchncs.de/tags/ThreatDetection" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ThreatDetection</span></a></p><p><a href="https://netzpalaver.de/2025/06/03/cyberkriminelle-nutzen-falsch-konfiguriertes-ki-tool-um-ki-generierte-payloads-auszufuehren/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">netzpalaver.de/2025/06/03/cybe</span><span class="invisible">rkriminelle-nutzen-falsch-konfiguriertes-ki-tool-um-ki-generierte-payloads-auszufuehren/</span></a></p>
adingbatponder<p><a href="https://fosstodon.org/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://fosstodon.org/tags/ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollama</span></a> <a href="https://fosstodon.org/tags/Llama3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Llama3</span></a> <a href="https://fosstodon.org/tags/nixos" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nixos</span></a> <a href="https://fosstodon.org/tags/proxmox" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>proxmox</span></a> <a href="https://fosstodon.org/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a> <a href="https://fosstodon.org/tags/nvidia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nvidia</span></a> <a href="https://fosstodon.org/tags/Nvidia" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Nvidia</span></a> <a href="https://fosstodon.org/tags/a4000" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>a4000</span></a> <a href="https://fosstodon.org/tags/GPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GPU</span></a> <a href="https://fosstodon.org/tags/tailnet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tailnet</span></a> <a href="https://fosstodon.org/tags/tailscale" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tailscale</span></a> <a href="https://fosstodon.org/tags/pciepassthrough" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pciepassthrough</span></a> <a href="https://fosstodon.org/tags/HomeLab" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HomeLab</span></a> <a href="https://fosstodon.org/tags/SelfHost" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SelfHost</span></a> <a href="https://fosstodon.org/tags/SelfHosting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SelfHosting</span></a> <a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://fosstodon.org/tags/vm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vm</span></a> <a href="https://fosstodon.org/tags/NixOS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NixOS</span></a> <br><a href="https://youtu.be/9hni6rLfMTg" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/9hni6rLfMTg</span><span class="invisible"></span></a></p>
Bora M. Alper<p>Self-hosted <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a>'s are so much fun, and I am very impressed how quickly FOSS ecosystem caught up with it.</p><p>I just installed <a href="https://mastodon.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> [0] + <a href="https://mastodon.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> [1] (bundled) to my midsize VPS tonight in less than 30 mins and was able to run small (≤ 3b) models on *CPU* with good performance.</p><p>[0] <a href="https://github.com/open-webui/open-webui" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/open-webui/open-web</span><span class="invisible">ui</span></a></p><p>[1] <a href="https://ollama.com/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ollama.com/</span><span class="invisible"></span></a></p>
Stéphane Klein<p>Je viens de publier un playground de déploiement de <a href="https://social.coop/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> connecté à la Generative API de <a href="https://social.coop/tags/Scaleway" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Scaleway</span></a> </p><p><a href="https://github.com/stephane-klein/open-webui-deployment-playground/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/stephane-klein/open</span><span class="invisible">-webui-deployment-playground/</span></a></p><p><a href="https://social.coop/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://social.coop/tags/DevOps" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DevOps</span></a> <a href="https://social.coop/tags/Playground" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Playground</span></a></p>
Simon Dückert<p>Ich habe einen Mac mini mit <a href="https://chaos.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> (über <a href="https://chaos.social/tags/Docker" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Docker</span></a>) in einem <a href="https://chaos.social/tags/LAN" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LAN</span></a> (Port 3000) mit <a href="https://chaos.social/tags/Fritzbox" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Fritzbox</span></a> und will den per Portfreigabe aus dem Internet zugreifbar machen (über die externe IP der Fritzbox). Per HTTP geht das gut. Gibt es eine Anleitung, wie ich das konfigurieren muss, dass ich per HTTPS auf den Mac min zugreifen kann?</p>
Mike Stone<p><span class="h-card" translate="no"><a href="https://fosstodon.org/@Gina" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>Gina</span></a></span> If I had to choose, I'd probably go with <a href="https://fosstodon.org/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> (which has been mentioned several times already). It's licensed under the MIT license and the models are about as close to open source as you can get. When I play with LLMs, it's what I use. Locally run and with an API that could be used to integrate with other stuff. I also have <a href="https://fosstodon.org/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> to make things prettier. Both can run locally, though OpenWebUI can integrate with cloud LLMs too. Of course, tomorrow everything could change.</p>
apfeltalk :verified:<p>Deepseek Model R1 läuft lokal auf dem Mac Studio M3 Ultra<br>Das Large Language Modell R1 vom Chinesischen Startup Deepseek lässt sich ohne Probleme lokal auf einem vollausgebauten Mac Studio mit M3 Ultra installieren und betreiben. Aber nicht nur das: Es steht dann auch auf iPhone, iPads und Mac im gleichen Netzwerk zur <br><a href="https://www.apfeltalk.de/magazin/news/deepseek-model-r1-laeuft-lokal-auf-dem-mac-studio-m3-ultra/" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">apfeltalk.de/magazin/news/deep</span><span class="invisible">seek-model-r1-laeuft-lokal-auf-dem-mac-studio-m3-ultra/</span></a><br><a href="https://creators.social/tags/KI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KI</span></a> <a href="https://creators.social/tags/News" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>News</span></a> <a href="https://creators.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://creators.social/tags/GenerativeKI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeKI</span></a> <a href="https://creators.social/tags/KI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KI</span></a> <a href="https://creators.social/tags/KnstlicheIntelligenz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KnstlicheIntelligenz</span></a> <a href="https://creators.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> <a href="https://creators.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a></p>
Jcrabapple<p>I set up <a href="https://dmv.community/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> on one of my more powerful servers, and it is fantastic. I'm running a couple smaller local Llama models, and hooked up my Anthropic and OpenRouter API keys to get access to Claude and a bunch of other models including Mistral, DeepSeek, and others. I also linked up my Kagi search API key to give web search capabilities to the models that don't have a web index. I will probably lower my Kagi Ultimate subscription to Professional since I no longer have a need for their Assistant.</p><p><a href="https://dmv.community/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://dmv.community/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://dmv.community/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> <a href="https://dmv.community/tags/selfhosted" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>selfhosted</span></a> <a href="https://dmv.community/tags/selfhosting" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>selfhosting</span></a></p>
Andreas Bulling<p>Do you have access to a GPU card, or maybe even multiple ones? <br>Are you interested in running a state-of-the-art <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/chatbot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatbot</span></a> locally, i.e. without paying <a href="https://mastodon.social/tags/openai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openai</span></a> et al. and in a privacy-preserving fashion?</p><p>Then <a href="https://mastodon.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> with the <a href="https://mastodon.social/tags/deepseek" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deepseek</span></a> model and <a href="https://mastodon.social/tags/Firefox" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Firefox</span></a> might be an interesting (and, I can attest, very well working) combination.</p><p><a href="https://github.com/open-webui/open-webui" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/open-webui/open-web</span><span class="invisible">ui</span></a></p><p><a href="https://docs.openwebui.com/tutorials/integrations/firefox-sidebar/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">docs.openwebui.com/tutorials/i</span><span class="invisible">ntegrations/firefox-sidebar/</span></a></p>
Al Audet<p><span class="h-card" translate="no"><a href="https://sfba.social/@skykiss" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>skykiss</span></a></span> That's why you download the model and use it on your local system only. <a href="https://fosstodon.org/tags/deepseek" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deepseek</span></a> <a href="https://fosstodon.org/tags/ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollama</span></a> <a href="https://fosstodon.org/tags/ollamacuda" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollamacuda</span></a> <a href="https://fosstodon.org/tags/docker" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>docker</span></a> <a href="https://fosstodon.org/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a></p>
Mike :nixos:<p>I was sooo inspired by just HOW easy it was to set up a local LLM with a nice web UI on <a href="https://fosstodon.org/tags/nixos" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nixos</span></a> that I made a quick video.</p><p>Seriously, well done <a href="https://fosstodon.org/tags/ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollama</span></a> <a href="https://fosstodon.org/tags/nixos" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nixos</span></a> <a href="https://fosstodon.org/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a> </p><p><a href="https://youtu.be/DGI2Dof2QSo" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/DGI2Dof2QSo</span><span class="invisible"></span></a></p>
Simon Dückert<p><a href="https://colearn.social/tags/TIL" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TIL</span></a> Aufsetzen einer eigenen Chatbot-Plattform auf Basis <a href="https://colearn.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> mit Anbindung an GPT-4o (über API) auf einem neu aufgesetzten Hetzner-Server inkl. Einrichtung <a href="https://colearn.social/tags/ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollama</span></a> und <a href="https://colearn.social/tags/nginx" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nginx</span></a> (für Reverse Proxy und SSL-Verschlüsselung) braucht nur knapp 45 Minuten 😎</p>
Angozi<p>Thanks to this video by NetworkChuck we are setting up our own <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> locally in studio using <a href="https://mastodon.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> and <a href="https://mastodon.social/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a> to break free from similar cloud based services widely reported to use unreasonable amounts of energy and water resources. This will also empower us to choose more ethically-trained <a href="https://mastodon.social/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a> models over time.<br><a href="https://m.youtube.com/watch?v=Wjrdr0NU4Sk" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">m.youtube.com/watch?v=Wjrdr0NU</span><span class="invisible">4Sk</span></a><br><a href="https://mastodon.social/tags/LocalAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LocalAI</span></a> <a href="https://mastodon.social/tags/OpenSourceAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSourceAI</span></a> <a href="https://mastodon.social/tags/EthicalChoices" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>EthicalChoices</span></a></p>
Simon Dückert<p>Bisher war meine Frau noch nicht so überzeugt von LLMs. Aber mit der Anwendung, mit allen Elternbriefen der Schule unserer Tochter im heimischen Intranet chatten zu können, habe ich ihr Interesse geweckt 😎</p><p>Für Technikinteressierte: habe <a href="https://colearn.social/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> und <a href="https://colearn.social/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> mit einem für deutsch feingetunten Llama 3.1 auf einem Macbook Air M1 laufen. Elternbriefe werden automatisch aus dem internen Bereich der Schule heruntergeladen und als Ordner mit PDFs als lokaler Informationsspeicher eingebunden (RAG).</p>
Websplaining<p>How To Setup Ollama LLM AI Chabot With Open WebUI, An Open-source AI User Interface On An Ubuntu VPS <a href="https://youtu.be/hGgy2uaUvo4" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/hGgy2uaUvo4</span><span class="invisible"></span></a> <a href="https://mastodon.online/tags/Websplaining" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Websplaining</span></a> <a href="https://mastodon.online/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ollama</span></a> <a href="https://mastodon.online/tags/OpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenWebUI</span></a> <a href="https://mastodon.online/tags/DigitalOcean" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DigitalOcean</span></a> <a href="https://mastodon.online/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.online/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.online/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ML</span></a> <a href="https://mastodon.online/tags/ChatBot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ChatBot</span></a> <a href="https://mastodon.online/tags/AiChatBot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AiChatBot</span></a> <a href="https://mastodon.online/tags/AiAssistant" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AiAssistant</span></a> <a href="https://mastodon.online/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> <a href="https://mastodon.online/tags/AiModels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AiModels</span></a> <a href="https://mastodon.online/tags/CharacterAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CharacterAI</span></a> <a href="https://mastodon.online/tags/CharacterAiModel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CharacterAiModel</span></a> <a href="https://mastodon.online/tags/BaseModel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BaseModel</span></a> <a href="https://mastodon.online/tags/WebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>WebUI</span></a> <a href="https://mastodon.online/tags/UI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>UI</span></a> <a href="https://mastodon.online/tags/AiUserInterface" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AiUserInterface</span></a> <a href="https://mastodon.online/tags/AiDashboard" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AiDashboard</span></a> <a href="https://mastodon.online/tags/VPS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VPS</span></a> <a href="https://mastodon.online/tags/Ubuntu" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Ubuntu</span></a> <a href="https://mastodon.online/tags/UbuntuLinux" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>UbuntuLinux</span></a> <a href="https://mastodon.online/tags/VirtualPrivateServer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VirtualPrivateServer</span></a> <a href="https://mastodon.online/tags/Cloud" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cloud</span></a> <a href="https://mastodon.online/tags/CloudServer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CloudServer</span></a> <a href="https://mastodon.online/tags/Droplet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Droplet</span></a> <a href="https://mastodon.online/tags/OllamaWithOpenWebUI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OllamaWithOpenWebUI</span></a> <a href="https://mastodon.online/tags/VirtualMachine" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VirtualMachine</span></a> <a href="https://mastodon.online/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://mastodon.online/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.online/tags/LargeLanguageModel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LargeLanguageModel</span></a></p>
Thomas Renkert🦞<p>Ich durfte gestern beim "Heidelberger Informatiklehrkräftetag" (<a href="https://hcommons.social/tags/HILT" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HILT</span></a>) Lehrer:innen der <a href="https://hcommons.social/tags/Informatik" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Informatik</span></a> zeigen, wie man sein eigenes <a href="https://hcommons.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> GRATIS finetunen kann - in unserem Fall <a href="https://hcommons.social/tags/Llama3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Llama3</span></a> und <a href="https://hcommons.social/tags/Phi3" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Phi3</span></a> - mit der <a href="https://hcommons.social/tags/MacgAIver" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MacgAIver</span></a> Pipeline. </p><p>Das Ziel ist dabei nicht (nur), Geld zu sparen, sondern mit einfachen Mitteln für mehr <a href="https://hcommons.social/tags/KIMuendigkeit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KIMuendigkeit</span></a> zu sorgen, indem Schüler:innen einen kleinen Blick unter die Motorhaube von Sprachmodellen werfen können.</p><p>Dabei helfen uns u.a. <a href="https://hcommons.social/tags/ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ollama</span></a>, <a href="https://hcommons.social/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a>, <a href="https://hcommons.social/tags/llamafactory" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llamafactory</span></a> und <a href="https://hcommons.social/tags/llamacpp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llamacpp</span></a>, aber auch Grundwissen aus den Geisteswissenschaften (bzw. den Fächern Deutsch, Englisch, Geschichte...), um zu einem tiefergehenden Verständnis von <a href="https://hcommons.social/tags/genAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>genAI</span></a> und seinen Umgang mit unserem "kulturellen Archiv" zu gelangen.</p><p>Es hat Spaß gemacht!</p><p>Für künftige MacgAIver-Ideen kann man dieser Gruppe folgen: <span class="h-card"><a href="https://a.gup.pe/u/macgaiver" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>macgaiver</span></a></span> </p><p><a href="https://hcommons.social/tags/fediLZ" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>fediLZ</span></a> <a href="https://hcommons.social/tags/lernenmitKI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>lernenmitKI</span></a> <a href="https://hcommons.social/tags/KI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KI</span></a> <a href="https://hcommons.social/tags/edubw" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>edubw</span></a> <a href="https://hcommons.social/tags/bildung" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>bildung</span></a> <a href="https://hcommons.social/tags/Heidelberg" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Heidelberg</span></a> <a href="https://hcommons.social/tags/education" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>education</span></a> <a href="https://hcommons.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://hcommons.social/tags/aieducation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aieducation</span></a> <a href="https://hcommons.social/tags/genAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>genAI</span></a> <a href="https://hcommons.social/tags/Informatikunterricht" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Informatikunterricht</span></a> <a href="https://hcommons.social/tags/Medienkompetenz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Medienkompetenz</span></a> <a href="https://hcommons.social/tags/InformatikEdu" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>InformatikEdu</span></a> <a href="https://hcommons.social/tags/AILiteracy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AILiteracy</span></a></p><p><span class="h-card"><a href="https://a.gup.pe/u/education" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>education</span></a></span> <span class="h-card"><a href="https://a.gup.pe/u/edutooters" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>edutooters</span></a></span></p>
Thomas Renkert🦞<p>Wer im Sinn von <a href="https://hcommons.social/tags/KIM%C3%BCndigkeit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KIMündigkeit</span></a> die Motorhaube zwei Millimeter öffnen möchte (lokal, ganz ohne Kosten, eigenen Server oder GPU): </p><p>1. <a href="https://hcommons.social/tags/openwebui" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openwebui</span></a> installieren: <a href="https://github.com/open-webui/open-webui" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/open-webui/open-web</span><span class="invisible">ui</span></a></p><p>2. Ollama.ai Modell "phi3.5" laden </p><p>3. Sofort loschatten, Dokumente ins <a href="https://hcommons.social/tags/RAG" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RAG</span></a> laden, im Web suchen... </p><p><a href="https://hcommons.social/tags/LernenmitKI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LernenmitKI</span></a></p>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload